visual-explanation
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill suggests using the
vporpnpmCLI to download and run thecomark-linterandcomark-uipackages. It also mentions fetching a skill component from the author's account (onmax/comark-ui). These downloads are used to support the rendering and validation of the visual explanations described in the instructions. - [COMMAND_EXECUTION]: The
SKILL.mdfile includes a shell command for linting documentation (vp dlx ... lint-comark explanation.md). This is a legitimate quality-assurance step for verifying the visual document's formatting before it is finalized. - [INDIRECT_PROMPT_INJECTION]: The skill involves reading source code and external data to create diagrams, creating a surface for potential indirect prompt injection. However, the risk is minimal because the instructions focus on producing static visual layouts (Mermaid, file trees), and the skill does not grant the agent high-privilege capabilities or access to sensitive data during the process.
Audit Metadata